diff options
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/audit_watch.c | 4 | ||||
-rw-r--r-- | kernel/auditsc.c | 9 | ||||
-rw-r--r-- | kernel/cgroup.c | 4 | ||||
-rw-r--r-- | kernel/cred.c | 4 | ||||
-rw-r--r-- | kernel/debug/debug_core.c | 2 | ||||
-rw-r--r-- | kernel/debug/kdb/kdb_main.c | 2 | ||||
-rw-r--r-- | kernel/debug/kdb/kdb_private.h | 7 | ||||
-rw-r--r-- | kernel/debug/kdb/kdb_support.c | 4 | ||||
-rw-r--r-- | kernel/exit.c | 12 | ||||
-rw-r--r-- | kernel/fork.c | 17 | ||||
-rw-r--r-- | kernel/kexec.c | 8 | ||||
-rw-r--r-- | kernel/kfifo.c | 753 | ||||
-rw-r--r-- | kernel/kmod.c | 4 | ||||
-rw-r--r-- | kernel/panic.c | 60 | ||||
-rw-r--r-- | kernel/params.c | 233 | ||||
-rw-r--r-- | kernel/pid.c | 56 | ||||
-rw-r--r-- | kernel/pm_qos_params.c | 12 | ||||
-rw-r--r-- | kernel/power/poweroff.c | 2 | ||||
-rw-r--r-- | kernel/ptrace.c | 12 | ||||
-rw-r--r-- | kernel/sched.c | 10 | ||||
-rw-r--r-- | kernel/sched_fair.c | 2 | ||||
-rw-r--r-- | kernel/time/timekeeping.c | 41 | ||||
-rw-r--r-- | kernel/trace/blktrace.c | 8 | ||||
-rw-r--r-- | kernel/trace/ring_buffer.c | 3 | ||||
-rw-r--r-- | kernel/trace/trace.c | 11 | ||||
-rw-r--r-- | kernel/trace/trace_events.c | 207 | ||||
-rw-r--r-- | kernel/trace/trace_functions_graph.c | 10 | ||||
-rw-r--r-- | kernel/trace/trace_stack.c | 2 | ||||
-rw-r--r-- | kernel/watchdog.c | 3 | ||||
-rw-r--r-- | kernel/workqueue.c | 9 |
30 files changed, 982 insertions, 529 deletions
diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 6bf2306be7d6..f0c9b2e7542d 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -526,8 +526,8 @@ static int audit_watch_handle_event(struct fsnotify_group *group, BUG_ON(group != audit_watch_group); switch (event->data_type) { - case (FSNOTIFY_EVENT_FILE): - inode = event->file->f_path.dentry->d_inode; + case (FSNOTIFY_EVENT_PATH): + inode = event->path.dentry->d_inode; break; case (FSNOTIFY_EVENT_INODE): inode = event->inode; diff --git a/kernel/auditsc.c b/kernel/auditsc.c index b87a63beb66c..1b31c130d034 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -1835,13 +1835,8 @@ void __audit_getname(const char *name) context->names[context->name_count].ino = (unsigned long)-1; context->names[context->name_count].osid = 0; ++context->name_count; - if (!context->pwd.dentry) { - read_lock(¤t->fs->lock); - context->pwd = current->fs->pwd; - path_get(¤t->fs->pwd); - read_unlock(¤t->fs->lock); - } - + if (!context->pwd.dentry) + get_fs_pwd(current->fs, &context->pwd); } /* audit_putname - intercept a putname request diff --git a/kernel/cgroup.c b/kernel/cgroup.c index d83cab06da87..192f88c5b0f9 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -1102,7 +1102,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) if (opts->release_agent) return -EINVAL; opts->release_agent = - kstrndup(token + 14, PATH_MAX, GFP_KERNEL); + kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL); if (!opts->release_agent) return -ENOMEM; } else if (!strncmp(token, "name=", 5)) { @@ -1123,7 +1123,7 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts) if (opts->name) return -EINVAL; opts->name = kstrndup(name, - MAX_CGROUP_ROOT_NAMELEN, + MAX_CGROUP_ROOT_NAMELEN - 1, GFP_KERNEL); if (!opts->name) return -ENOMEM; diff --git a/kernel/cred.c b/kernel/cred.c index 60bc8b1e32e6..9a3e22641fe7 100644 --- a/kernel/cred.c +++ b/kernel/cred.c @@ -22,10 +22,6 @@ #define kdebug(FMT, ...) \ printk("[%-5.5s%5u] "FMT"\n", current->comm, current->pid ,##__VA_ARGS__) #else -static inline __attribute__((format(printf, 1, 2))) -void no_printk(const char *fmt, ...) -{ -} #define kdebug(FMT, ...) \ no_printk("[%-5.5s%5u] "FMT"\n", current->comm, current->pid ,##__VA_ARGS__) #endif diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c index 3c2d4972d235..de407c78178d 100644 --- a/kernel/debug/debug_core.c +++ b/kernel/debug/debug_core.c @@ -741,7 +741,7 @@ static struct console kgdbcons = { }; #ifdef CONFIG_MAGIC_SYSRQ -static void sysrq_handle_dbg(int key, struct tty_struct *tty) +static void sysrq_handle_dbg(int key) { if (!dbg_io_ops) { printk(KERN_CRIT "ERROR: No KGDB I/O module available\n"); diff --git a/kernel/debug/kdb/kdb_main.c b/kernel/debug/kdb/kdb_main.c index 28b844118bbd..caf057a3de0e 100644 --- a/kernel/debug/kdb/kdb_main.c +++ b/kernel/debug/kdb/kdb_main.c @@ -1929,7 +1929,7 @@ static int kdb_sr(int argc, const char **argv) if (argc != 1) return KDB_ARGCOUNT; kdb_trap_printk++; - __handle_sysrq(*argv[1], NULL, 0); + __handle_sysrq(*argv[1], false); kdb_trap_printk--; return 0; diff --git a/kernel/debug/kdb/kdb_private.h b/kernel/debug/kdb/kdb_private.h index c438f545a321..be775f7e81e0 100644 --- a/kernel/debug/kdb/kdb_private.h +++ b/kernel/debug/kdb/kdb_private.h @@ -255,7 +255,14 @@ extern void kdb_ps1(const struct task_struct *p); extern void kdb_print_nameval(const char *name, unsigned long val); extern void kdb_send_sig_info(struct task_struct *p, struct siginfo *info); extern void kdb_meminfo_proc_show(void); +#ifdef CONFIG_KALLSYMS extern const char *kdb_walk_kallsyms(loff_t *pos); +#else /* ! CONFIG_KALLSYMS */ +static inline const char *kdb_walk_kallsyms(loff_t *pos) +{ + return NULL; +} +#endif /* ! CONFIG_KALLSYMS */ extern char *kdb_getstr(char *, size_t, char *); /* Defines for kdb_symbol_print */ diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c index 45344d5c53dd..6b2485dcb050 100644 --- a/kernel/debug/kdb/kdb_support.c +++ b/kernel/debug/kdb/kdb_support.c @@ -82,8 +82,8 @@ static char *kdb_name_table[100]; /* arbitrary size */ int kdbnearsym(unsigned long addr, kdb_symtab_t *symtab) { int ret = 0; - unsigned long symbolsize; - unsigned long offset; + unsigned long symbolsize = 0; + unsigned long offset = 0; #define knt1_size 128 /* must be >= kallsyms table size */ char *knt1 = NULL; diff --git a/kernel/exit.c b/kernel/exit.c index ceffc67b564a..03120229db28 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -771,9 +771,12 @@ static void forget_original_parent(struct task_struct *father) struct task_struct *p, *n, *reaper; LIST_HEAD(dead_children); - exit_ptrace(father); - write_lock_irq(&tasklist_lock); + /* + * Note that exit_ptrace() and find_new_reaper() might + * drop tasklist_lock and reacquire it. + */ + exit_ptrace(father); reaper = find_new_reaper(father); list_for_each_entry_safe(p, n, &father->children, sibling) { @@ -1383,8 +1386,7 @@ static int wait_task_stopped(struct wait_opts *wo, if (!unlikely(wo->wo_flags & WNOWAIT)) *p_code = 0; - /* don't need the RCU readlock here as we're holding a spinlock */ - uid = __task_cred(p)->uid; + uid = task_uid(p); unlock_sig: spin_unlock_irq(&p->sighand->siglock); if (!exit_code) @@ -1457,7 +1459,7 @@ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) } if (!unlikely(wo->wo_flags & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; - uid = __task_cred(p)->uid; + uid = task_uid(p); spin_unlock_irq(&p->sighand->siglock); pid = task_pid_vnr(p); diff --git a/kernel/fork.c b/kernel/fork.c index 98b450876f93..b7e9d60a675d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -300,7 +300,7 @@ out: #ifdef CONFIG_MMU static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) { - struct vm_area_struct *mpnt, *tmp, **pprev; + struct vm_area_struct *mpnt, *tmp, *prev, **pprev; struct rb_node **rb_link, *rb_parent; int retval; unsigned long charge; @@ -328,6 +328,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) if (retval) goto out; + prev = NULL; for (mpnt = oldmm->mmap; mpnt; mpnt = mpnt->vm_next) { struct file *file; @@ -359,7 +360,7 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) goto fail_nomem_anon_vma_fork; tmp->vm_flags &= ~VM_LOCKED; tmp->vm_mm = mm; - tmp->vm_next = NULL; + tmp->vm_next = tmp->vm_prev = NULL; file = tmp->vm_file; if (file) { struct inode *inode = file->f_path.dentry->d_inode; @@ -392,6 +393,8 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm) */ *pprev = tmp; pprev = &tmp->vm_next; + tmp->vm_prev = prev; + prev = tmp; __vma_link_rb(mm, tmp, rb_link, rb_parent); rb_link = &tmp->vm_rb.rb_right; @@ -752,13 +755,13 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk) struct fs_struct *fs = current->fs; if (clone_flags & CLONE_FS) { /* tsk->fs is already what we want */ - write_lock(&fs->lock); + spin_lock(&fs->lock); if (fs->in_exec) { - write_unlock(&fs->lock); + spin_unlock(&fs->lock); return -EAGAIN; } fs->users++; - write_unlock(&fs->lock); + spin_unlock(&fs->lock); return 0; } tsk->fs = copy_fs_struct(fs); @@ -1676,13 +1679,13 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags) if (new_fs) { fs = current->fs; - write_lock(&fs->lock); + spin_lock(&fs->lock); current->fs = new_fs; if (--fs->users) new_fs = NULL; else new_fs = fs; - write_unlock(&fs->lock); + spin_unlock(&fs->lock); } if (new_mm) { diff --git a/kernel/kexec.c b/kernel/kexec.c index 131b1703936f..c0613f7d6730 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -151,8 +151,10 @@ static int do_kimage_alloc(struct kimage **rimage, unsigned long entry, image->nr_segments = nr_segments; segment_bytes = nr_segments * sizeof(*segments); result = copy_from_user(image->segment, segments, segment_bytes); - if (result) + if (result) { + result = -EFAULT; goto out; + } /* * Verify we have good destination addresses. The caller is @@ -827,7 +829,7 @@ static int kimage_load_normal_segment(struct kimage *image, result = copy_from_user(ptr, buf, uchunk); kunmap(page); if (result) { - result = (result < 0) ? result : -EIO; + result = -EFAULT; goto out; } ubytes -= uchunk; @@ -882,7 +884,7 @@ static int kimage_load_crash_segment(struct kimage *image, kexec_flush_icache_page(page); kunmap(page); if (result) { - result = (result < 0) ? result : -EIO; + result = -EFAULT; goto out; } ubytes -= uchunk; diff --git a/kernel/kfifo.c b/kernel/kfifo.c index 35edbe22e9a9..6b5580c57644 100644 --- a/kernel/kfifo.c +++ b/kernel/kfifo.c @@ -1,8 +1,7 @@ /* - * A generic kernel FIFO implementation. + * A generic kernel FIFO implementation * - * Copyright (C) 2009 Stefani Seibold <stefani@seibold.net> - * Copyright (C) 2004 Stelian Pop <stelian@popies.net> + * Copyright (C) 2009/2010 Stefani Seibold <stefani@seibold.net> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -11,7 +10,7 @@ * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License @@ -24,422 +23,588 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/err.h> -#include <linux/kfifo.h> #include <linux/log2.h> #include <linux/uaccess.h> +#include <linux/kfifo.h> -static void _kfifo_init(struct kfifo *fifo, void *buffer, - unsigned int size) -{ - fifo->buffer = buffer; - fifo->size = size; - - kfifo_reset(fifo); -} - -/** - * kfifo_init - initialize a FIFO using a preallocated buffer - * @fifo: the fifo to assign the buffer - * @buffer: the preallocated buffer to be used. - * @size: the size of the internal buffer, this has to be a power of 2. - * +/* + * internal helper to calculate the unused elements in a fifo */ -void kfifo_init(struct kfifo *fifo, void *buffer, unsigned int size) +static inline unsigned int kfifo_unused(struct __kfifo *fifo) { - /* size must be a power of 2 */ - BUG_ON(!is_power_of_2(size)); - - _kfifo_init(fifo, buffer, size); + return (fifo->mask + 1) - (fifo->in - fifo->out); } -EXPORT_SYMBOL(kfifo_init); -/** - * kfifo_alloc - allocates a new FIFO internal buffer - * @fifo: the fifo to assign then new buffer - * @size: the size of the buffer to be allocated, this have to be a power of 2. - * @gfp_mask: get_free_pages mask, passed to kmalloc() - * - * This function dynamically allocates a new fifo internal buffer - * - * The size will be rounded-up to a power of 2. - * The buffer will be release with kfifo_free(). - * Return 0 if no error, otherwise the an error code - */ -int kfifo_alloc(struct kfifo *fifo, unsigned int size, gfp_t gfp_mask) +int __kfifo_alloc(struct __kfifo *fifo, unsigned int size, + size_t esize, gfp_t gfp_mask) { - unsigned char *buffer; - /* - * round up to the next power of 2, since our 'let the indices + * round down to the next power of 2, since our 'let the indices * wrap' technique works only in this case. */ - if (!is_power_of_2(size)) { - BUG_ON(size > 0x80000000); - size = roundup_pow_of_two(size); + if (!is_power_of_2(size)) + size = rounddown_pow_of_two(size); + + fifo->in = 0; + fifo->out = 0; + fifo->esize = esize; + + if (size < 2) { + fifo->data = NULL; + fifo->mask = 0; + return -EINVAL; } - buffer = kmalloc(size, gfp_mask); - if (!buffer) { - _kfifo_init(fifo, NULL, 0); + fifo->data = kmalloc(size * esize, gfp_mask); + + if (!fifo->data) { + fifo->mask = 0; return -ENOMEM; } - - _kfifo_init(fifo, buffer, size); + fifo->mask = size - 1; return 0; } -EXPORT_SYMBOL(kfifo_alloc); +EXPORT_SYMBOL(__kfifo_alloc); -/** - * kfifo_free - frees the FIFO internal buffer - * @fifo: the fifo to be freed. - */ -void kfifo_free(struct kfifo *fifo) +void __kfifo_free(struct __kfifo *fifo) { - kfree(fifo->buffer); - _kfifo_init(fifo, NULL, 0); + kfree(fifo->data); + fifo->in = 0; + fifo->out = 0; + fifo->esize = 0; + fifo->data = NULL; + fifo->mask = 0; } -EXPORT_SYMBOL(kfifo_free); +EXPORT_SYMBOL(__kfifo_free); -/** - * kfifo_skip - skip output data - * @fifo: the fifo to be used. - * @len: number of bytes to skip - */ -void kfifo_skip(struct kfifo *fifo, unsigned int len) +int __kfifo_init(struct __kfifo *fifo, void *buffer, + unsigned int size, size_t esize) { - if (len < kfifo_len(fifo)) { - __kfifo_add_out(fifo, len); - return; + size /= esize; + + if (!is_power_of_2(size)) + size = rounddown_pow_of_two(size); + + fifo->in = 0; + fifo->out = 0; + fifo->esize = esize; + fifo->data = buffer; + + if (size < 2) { + fifo->mask = 0; + return -EINVAL; } - kfifo_reset_out(fifo); + fifo->mask = size - 1; + + return 0; } -EXPORT_SYMBOL(kfifo_skip); +EXPORT_SYMBOL(__kfifo_init); -static inline void __kfifo_in_data(struct kfifo *fifo, - const void *from, unsigned int len, unsigned int off) +static void kfifo_copy_in(struct __kfifo *fifo, const void *src, + unsigned int len, unsigned int off) { + unsigned int size = fifo->mask + 1; + unsigned int esize = fifo->esize; unsigned int l; + off &= fifo->mask; + if (esize != 1) { + off *= esize; + size *= esize; + len *= esize; + } + l = min(len, size - off); + + memcpy(fifo->data + off, src, l); + memcpy(fifo->data, src + l, len - l); /* - * Ensure that we sample the fifo->out index -before- we - * start putting bytes into the kfifo. + * make sure that the data in the fifo is up to date before + * incrementing the fifo->in index counter */ + smp_wmb(); +} - smp_mb(); - - off = __kfifo_off(fifo, fifo->in + off); +unsigned int __kfifo_in(struct __kfifo *fifo, + const void *buf, unsigned int len) +{ + unsigned int l; - /* first put the data starting from fifo->in to buffer end */ - l = min(len, fifo->size - off); - memcpy(fifo->buffer + off, from, l); + l = kfifo_unused(fifo); + if (len > l) + len = l; - /* then put the rest (if any) at the beginning of the buffer */ - memcpy(fifo->buffer, from + l, len - l); + kfifo_copy_in(fifo, buf, len, fifo->in); + fifo->in += len; + return len; } +EXPORT_SYMBOL(__kfifo_in); -static inline void __kfifo_out_data(struct kfifo *fifo, - void *to, unsigned int len, unsigned int off) +static void kfifo_copy_out(struct __kfifo *fifo, void *dst, + unsigned int len, unsigned int off) { + unsigned int size = fifo->mask + 1; + unsigned int esize = fifo->esize; unsigned int l; + off &= fifo->mask; + if (esize != 1) { + off *= esize; + size *= esize; + len *= esize; + } + l = min(len, size - off); + + memcpy(dst, fifo->data + off, l); + memcpy(dst + l, fifo->data, len - l); /* - * Ensure that we sample the fifo->in index -before- we - * start removing bytes from the kfifo. + * make sure that the data is copied before + * incrementing the fifo->out index counter */ + smp_wmb(); +} - smp_rmb(); +unsigned int __kfifo_out_peek(struct __kfifo *fifo, + void *buf, unsigned int len) +{ + unsigned int l; - off = __kfifo_off(fifo, fifo->out + off); + l = fifo->in - fifo->out; + if (len > l) + len = l; - /* first get the data from fifo->out until the end of the buffer */ - l = min(len, fifo->size - off); - memcpy(to, fifo->buffer + off, l); + kfifo_copy_out(fifo, buf, len, fifo->out); + return len; +} +EXPORT_SYMBOL(__kfifo_out_peek); - /* then get the rest (if any) from the beginning of the buffer */ - memcpy(to + l, fifo->buffer, len - l); +unsigned int __kfifo_out(struct __kfifo *fifo, + void *buf, unsigned int len) +{ + len = __kfifo_out_peek(fifo, buf, len); + fifo->out += len; + return len; } +EXPORT_SYMBOL(__kfifo_out); -static inline int __kfifo_from_user_data(struct kfifo *fifo, - const void __user *from, unsigned int len, unsigned int off, - unsigned *lenout) +static unsigned long kfifo_copy_from_user(struct __kfifo *fifo, + const void __user *from, unsigned int len, unsigned int off, + unsigned int *copied) { + unsigned int size = fifo->mask + 1; + unsigned int esize = fifo->esize; unsigned int l; - int ret; + unsigned long ret; + off &= fifo->mask; + if (esize != 1) { + off *= esize; + size *= esize; + len *= esize; + } + l = min(len, size - off); + + ret = copy_from_user(fifo->data + off, from, l); + if (unlikely(ret)) + ret = DIV_ROUND_UP(ret + len - l, esize); + else { + ret = copy_from_user(fifo->data, from + l, len - l); + if (unlikely(ret)) + ret = DIV_ROUND_UP(ret, esize); + } /* - * Ensure that we sample the fifo->out index -before- we - * start putting bytes into the kfifo. + * make sure that the data in the fifo is up to date before + * incrementing the fifo->in index counter */ + smp_wmb(); + *copied = len - ret; + /* return the number of elements which are not copied */ + return ret; +} - smp_mb(); +int __kfifo_from_user(struct __kfifo *fifo, const void __user *from, + unsigned long len, unsigned int *copied) +{ + unsigned int l; + unsigned long ret; + unsigned int esize = fifo->esize; + int err; - off = __kfifo_off(fifo, fifo->in + off); + if (esize != 1) + len /= esize; - /* first put the data starting from fifo->in to buffer end */ - l = min(len, fifo->size - off); - ret = copy_from_user(fifo->buffer + off, from, l); - if (unlikely(ret)) { - *lenout = ret; - return -EFAULT; - } - *lenout = l; + l = kfifo_unused(fifo); + if (len > l) + len = l; - /* then put the rest (if any) at the beginning of the buffer */ - ret = copy_from_user(fifo->buffer, from + l, len - l); - *lenout += ret ? ret : len - l; - return ret ? -EFAULT : 0; + ret = kfifo_copy_from_user(fifo, from, len, fifo->in, copied); + if (unlikely(ret)) { + len -= ret; + err = -EFAULT; + } else + err = 0; + fifo->in += len; + return err; } +EXPORT_SYMBOL(__kfifo_from_user); -static inline int __kfifo_to_user_data(struct kfifo *fifo, - void __user *to, unsigned int len, unsigned int off, unsigned *lenout) +static unsigned long kfifo_copy_to_user(struct __kfifo *fifo, void __user *to, + unsigned int len, unsigned int off, unsigned int *copied) { unsigned int l; - int ret; - + unsigned long ret; + unsigned int size = fifo->mask + 1; + unsigned int esize = fifo->esize; + + off &= fifo->mask; + if (esize != 1) { + off *= esize; + size *= esize; + len *= esize; + } + l = min(len, size - off); + + ret = copy_to_user(to, fifo->data + off, l); + if (unlikely(ret)) + ret = DIV_ROUND_UP(ret + len - l, esize); + else { + ret = copy_to_user(to + l, fifo->data, len - l); + if (unlikely(ret)) + ret = DIV_ROUND_UP(ret, esize); + } /* - * Ensure that we sample the fifo->in index -before- we - * start removing bytes from the kfifo. + * make sure that the data is copied before + * incrementing the fifo->out index counter */ + smp_wmb(); + *copied = len - ret; + /* return the number of elements which are not copied */ + return ret; +} - smp_rmb(); +int __kfifo_to_user(struct __kfifo *fifo, void __user *to, + unsigned long len, unsigned int *copied) +{ + unsigned int l; + unsigned long ret; + unsigned int esize = fifo->esize; + int err; - off = __kfifo_off(fifo, fifo->out + off); + if (esize != 1) + len /= esize; - /* first get the data from fifo->out until the end of the buffer */ - l = min(len, fifo->size - off); - ret = copy_to_user(to, fifo->buffer + off, l); - *lenout = l; + l = fifo->in - fifo->out; + if (len > l) + len = l; + ret = kfifo_copy_to_user(fifo, to, len, fifo->out, copied); if (unlikely(ret)) { - *lenout -= ret; - return -EFAULT; - } + len -= ret; + err = -EFAULT; + } else + err = 0; + fifo->out += len; + return err; +} +EXPORT_SYMBOL(__kfifo_to_user); - /* then get the rest (if any) from the beginning of the buffer */ - len -= l; - ret = copy_to_user(to + l, fifo->buffer, len); - if (unlikely(ret)) { - *lenout += len - ret; - return -EFAULT; +static int setup_sgl_buf(struct scatterlist *sgl, void *buf, + int nents, unsigned int len) +{ + int n; + unsigned int l; + unsigned int off; + struct page *page; + + if (!nents) + return 0; + + if (!len) + return 0; + + n = 0; + page = virt_to_page(buf); + off = offset_in_page(buf); + l = 0; + + while (len >= l + PAGE_SIZE - off) { + struct page *npage; + + l += PAGE_SIZE; + buf += PAGE_SIZE; + npage = virt_to_page(buf); + if (page_to_phys(page) != page_to_phys(npage) - l) { + sg_set_page(sgl, page, l - off, off); + sgl = sg_next(sgl); + if (++n == nents || sgl == NULL) + return n; + page = npage; + len -= l - off; + l = off = 0; + } } - *lenout += len; - return 0; + sg_set_page(sgl, page, len, off); + return n + 1; } -unsigned int __kfifo_in_n(struct kfifo *fifo, - const void *from, unsigned int len, unsigned int recsize) +static unsigned int setup_sgl(struct __kfifo *fifo, struct scatterlist *sgl, + int nents, unsigned int len, unsigned int off) { - if (kfifo_avail(fifo) < len + recsize) - return len + 1; + unsigned int size = fifo->mask + 1; + unsigned int esize = fifo->esize; + unsigned int l; + unsigned int n; - __kfifo_in_data(fifo, from, len, recsize); - return 0; + off &= fifo->mask; + if (esize != 1) { + off *= esize; + size *= esize; + len *= esize; + } + l = min(len, size - off); + + n = setup_sgl_buf(sgl, fifo->data + off, nents, l); + n += setup_sgl_buf(sgl + n, fifo->data, nents - n, len - l); + + if (n) + sg_mark_end(sgl + n - 1); + return n; } -EXPORT_SYMBOL(__kfifo_in_n); -/** - * kfifo_in - puts some data into the FIFO - * @fifo: the fifo to be used. - * @from: the data to be added. - * @len: the length of the data to be added. - * - * This function copies at most @len bytes from the @from buffer into - * the FIFO depending on the free space, and returns the number of - * bytes copied. - * - * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these functions. - */ -unsigned int kfifo_in(struct kfifo *fifo, const void *from, - unsigned int len) +unsigned int __kfifo_dma_in_prepare(struct __kfifo *fifo, + struct scatterlist *sgl, int nents, unsigned int len) { - len = min(kfifo_avail(fifo), len); + unsigned int l; - __kfifo_in_data(fifo, from, len, 0); - __kfifo_add_in(fifo, len); - return len; + l = kfifo_unused(fifo); + if (len > l) + len = l; + + return setup_sgl(fifo, sgl, nents, len, fifo->in); } -EXPORT_SYMBOL(kfifo_in); +EXPORT_SYMBOL(__kfifo_dma_in_prepare); -unsigned int __kfifo_in_generic(struct kfifo *fifo, - const void *from, unsigned int len, unsigned int recsize) +unsigned int __kfifo_dma_out_prepare(struct __kfifo *fifo, + struct scatterlist *sgl, int nents, unsigned int len) { - return __kfifo_in_rec(fifo, from, len, recsize); + unsigned int l; + + l = fifo->in - fifo->out; + if (len > l) + len = l; + + return setup_sgl(fifo, sgl, nents, len, fifo->out); } -EXPORT_SYMBOL(__kfifo_in_generic); +EXPORT_SYMBOL(__kfifo_dma_out_prepare); -unsigned int __kfifo_out_n(struct kfifo *fifo, - void *to, unsigned int len, unsigned int recsize) +unsigned int __kfifo_max_r(unsigned int len, size_t recsize) { - if (kfifo_len(fifo) < len + recsize) - return len; + unsigned int max = (1 << (recsize << 3)) - 1; - __kfifo_out_data(fifo, to, len, recsize); - __kfifo_add_out(fifo, len + recsize); - return 0; + if (len > max) + return max; + return len; } -EXPORT_SYMBOL(__kfifo_out_n); -/** - * kfifo_out - gets some data from the FIFO - * @fifo: the fifo to be used. - * @to: where the data must be copied. - * @len: the size of the destination buffer. - * - * This function copies at most @len bytes from the FIFO into the - * @to buffer and returns the number of copied bytes. - * - * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these functions. +#define __KFIFO_PEEK(data, out, mask) \ + ((data)[(out) & (mask)]) +/* + * __kfifo_peek_n internal helper function for determinate the length of + * the next record in the fifo */ -unsigned int kfifo_out(struct kfifo *fifo, void *to, unsigned int len) +static unsigned int __kfifo_peek_n(struct __kfifo *fifo, size_t recsize) { - len = min(kfifo_len(fifo), len); + unsigned int l; + unsigned int mask = fifo->mask; + unsigned char *data = fifo->data; - __kfifo_out_data(fifo, to, len, 0); - __kfifo_add_out(fifo, len); + l = __KFIFO_PEEK(data, fifo->out, mask); - return len; + if (--recsize) + l |= __KFIFO_PEEK(data, fifo->out + 1, mask) << 8; + + return l; } -EXPORT_SYMBOL(kfifo_out); -/** - * kfifo_out_peek - copy some data from the FIFO, but do not remove it - * @fifo: the fifo to be used. - * @to: where the data must be copied. - * @len: the size of the destination buffer. - * @offset: offset into the fifo - * - * This function copies at most @len bytes at @offset from the FIFO - * into the @to buffer and returns the number of copied bytes. - * The data is not removed from the FIFO. +#define __KFIFO_POKE(data, in, mask, val) \ + ( \ + (data)[(in) & (mask)] = (unsigned char)(val) \ + ) + +/* + * __kfifo_poke_n internal helper function for storeing the length of + * the record into the fifo */ -unsigned int kfifo_out_peek(struct kfifo *fifo, void *to, unsigned int len, - unsigned offset) +static void __kfifo_poke_n(struct __kfifo *fifo, unsigned int n, size_t recsize) { - len = min(kfifo_len(fifo), len + offset); + unsigned int mask = fifo->mask; + unsigned char *data = fifo->data; - __kfifo_out_data(fifo, to, len, offset); - return len; + __KFIFO_POKE(data, fifo->in, mask, n); + + if (recsize > 1) + __KFIFO_POKE(data, fifo->in + 1, mask, n >> 8); } -EXPORT_SYMBOL(kfifo_out_peek); -unsigned int __kfifo_out_generic(struct kfifo *fifo, - void *to, unsigned int len, unsigned int recsize, - unsigned int *total) +unsigned int __kfifo_len_r(struct __kfifo *fifo, size_t recsize) { - return __kfifo_out_rec(fifo, to, len, recsize, total); + return __kfifo_peek_n(fifo, recsize); } -EXPORT_SYMBOL(__kfifo_out_generic); +EXPORT_SYMBOL(__kfifo_len_r); -unsigned int __kfifo_from_user_n(struct kfifo *fifo, - const void __user *from, unsigned int len, unsigned int recsize) +unsigned int __kfifo_in_r(struct __kfifo *fifo, const void *buf, + unsigned int len, size_t recsize) { - unsigned total; + if (len + recsize > kfifo_unused(fifo)) + return 0; - if (kfifo_avail(fifo) < len + recsize) - return len + 1; + __kfifo_poke_n(fifo, len, recsize); - __kfifo_from_user_data(fifo, from, len, recsize, &total); - return total; + kfifo_copy_in(fifo, buf, len, fifo->in + recsize); + fifo->in += len + recsize; + return len; } -EXPORT_SYMBOL(__kfifo_from_user_n); +EXPORT_SYMBOL(__kfifo_in_r); -/** - * kfifo_from_user - puts some data from user space into the FIFO - * @fifo: the fifo to be used. - * @from: pointer to the data to be added. - * @len: the length of the data to be added. - * @total: the actual returned data length. - * - * This function copies at most @len bytes from the @from into the - * FIFO depending and returns -EFAULT/0. - * - * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these functions. - */ -int kfifo_from_user(struct kfifo *fifo, - const void __user *from, unsigned int len, unsigned *total) -{ - int ret; - len = min(kfifo_avail(fifo), len); - ret = __kfifo_from_user_data(fifo, from, len, 0, total); - if (ret) - return ret; - __kfifo_add_in(fifo, len); - return 0; +static unsigned int kfifo_out_copy_r(struct __kfifo *fifo, + void *buf, unsigned int len, size_t recsize, unsigned int *n) +{ + *n = __kfifo_peek_n(fifo, recsize); + + if (len > *n) + len = *n; + + kfifo_copy_out(fifo, buf, len, fifo->out + recsize); + return len; } -EXPORT_SYMBOL(kfifo_from_user); -unsigned int __kfifo_from_user_generic(struct kfifo *fifo, - const void __user *from, unsigned int len, unsigned int recsize) +unsigned int __kfifo_out_peek_r(struct __kfifo *fifo, void *buf, + unsigned int len, size_t recsize) { - return __kfifo_from_user_rec(fifo, from, len, recsize); + unsigned int n; + + if (fifo->in == fifo->out) + return 0; + + return kfifo_out_copy_r(fifo, buf, len, recsize, &n); } -EXPORT_SYMBOL(__kfifo_from_user_generic); +EXPORT_SYMBOL(__kfifo_out_peek_r); -unsigned int __kfifo_to_user_n(struct kfifo *fifo, - void __user *to, unsigned int len, unsigned int reclen, - unsigned int recsize) +unsigned int __kfifo_out_r(struct __kfifo *fifo, void *buf, + unsigned int len, size_t recsize) { - unsigned int ret, total; + unsigned int n; - if (kfifo_len(fifo) < reclen + recsize) - return len; + if (fifo->in == fifo->out) + return 0; - ret = __kfifo_to_user_data(fifo, to, reclen, recsize, &total); + len = kfifo_out_copy_r(fifo, buf, len, recsize, &n); + fifo->out += n + recsize; + return len; +} +EXPORT_SYMBOL(__kfifo_out_r); - if (likely(ret == 0)) - __kfifo_add_out(fifo, reclen + recsize); +void __kfifo_skip_r(struct __kfifo *fifo, size_t recsize) +{ + unsigned int n; - return total; + n = __kfifo_peek_n(fifo, recsize); + fifo->out += n + recsize; } -EXPORT_SYMBOL(__kfifo_to_user_n); +EXPORT_SYMBOL(__kfifo_skip_r); -/** - * kfifo_to_user - gets data from the FIFO and write it to user space - * @fifo: the fifo to be used. - * @to: where the data must be copied. - * @len: the size of the destination buffer. - * @lenout: pointer to output variable with copied data - * - * This function copies at most @len bytes from the FIFO into the - * @to buffer and 0 or -EFAULT. - * - * Note that with only one concurrent reader and one concurrent - * writer, you don't need extra locking to use these functions. - */ -int kfifo_to_user(struct kfifo *fifo, - void __user *to, unsigned int len, unsigned *lenout) +int __kfifo_from_user_r(struct __kfifo *fifo, const void __user *from, + unsigned long len, unsigned int *copied, size_t recsize) { - int ret; - len = min(kfifo_len(fifo), len); - ret = __kfifo_to_user_data(fifo, to, len, 0, lenout); - __kfifo_add_out(fifo, *lenout); - return ret; + unsigned long ret; + + len = __kfifo_max_r(len, recsize); + + if (len + recsize > kfifo_unused(fifo)) { + *copied = 0; + return 0; + } + + __kfifo_poke_n(fifo, len, recsize); + + ret = kfifo_copy_from_user(fifo, from, len, fifo->in + recsize, copied); + if (unlikely(ret)) { + *copied = 0; + return -EFAULT; + } + fifo->in += len + recsize; + return 0; } -EXPORT_SYMBOL(kfifo_to_user); +EXPORT_SYMBOL(__kfifo_from_user_r); -unsigned int __kfifo_to_user_generic(struct kfifo *fifo, - void __user *to, unsigned int len, unsigned int recsize, - unsigned int *total) +int __kfifo_to_user_r(struct __kfifo *fifo, void __user *to, + unsigned long len, unsigned int *copied, size_t recsize) { - return __kfifo_to_user_rec(fifo, to, len, recsize, total); + unsigned long ret; + unsigned int n; + + if (fifo->in == fifo->out) { + *copied = 0; + return 0; + } + + n = __kfifo_peek_n(fifo, recsize); + if (len > n) + len = n; + + ret = kfifo_copy_to_user(fifo, to, len, fifo->out + recsize, copied); + if (unlikely(ret)) { + *copied = 0; + return -EFAULT; + } + fifo->out += n + recsize; + return 0; } -EXPORT_SYMBOL(__kfifo_to_user_generic); +EXPORT_SYMBOL(__kfifo_to_user_r); -unsigned int __kfifo_peek_generic(struct kfifo *fifo, unsigned int recsize) +unsigned int __kfifo_dma_in_prepare_r(struct __kfifo *fifo, + struct scatterlist *sgl, int nents, unsigned int len, size_t recsize) { - if (recsize == 0) - return kfifo_avail(fifo); + if (!nents) + BUG(); - return __kfifo_peek_n(fifo, recsize); + len = __kfifo_max_r(len, recsize); + + if (len + recsize > kfifo_unused(fifo)) + return 0; + + return setup_sgl(fifo, sgl, nents, len, fifo->in + recsize); } -EXPORT_SYMBOL(__kfifo_peek_generic); +EXPORT_SYMBOL(__kfifo_dma_in_prepare_r); -void __kfifo_skip_generic(struct kfifo *fifo, unsigned int recsize) +void __kfifo_dma_in_finish_r(struct __kfifo *fifo, + unsigned int len, size_t recsize) { - __kfifo_skip_rec(fifo, recsize); + len = __kfifo_max_r(len, recsize); + __kfifo_poke_n(fifo, len, recsize); + fifo->in += len + recsize; } -EXPORT_SYMBOL(__kfifo_skip_generic); +EXPORT_SYMBOL(__kfifo_dma_in_finish_r); +unsigned int __kfifo_dma_out_prepare_r(struct __kfifo *fifo, + struct scatterlist *sgl, int nents, unsigned int len, size_t recsize) +{ + if (!nents) + BUG(); + + len = __kfifo_max_r(len, recsize); + + if (len + recsize > fifo->in - fifo->out) + return 0; + + return setup_sgl(fifo, sgl, nents, len, fifo->out + recsize); +} +EXPORT_SYMBOL(__kfifo_dma_out_prepare_r); + +void __kfifo_dma_out_finish_r(struct __kfifo *fifo, size_t recsize) +{ + unsigned int len; + + len = __kfifo_peek_n(fifo, recsize); + fifo->out += len + recsize; +} +EXPORT_SYMBOL(__kfifo_dma_out_finish_r); diff --git a/kernel/kmod.c b/kernel/kmod.c index 6e9b19667a8d..9cd0591c96a2 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -153,7 +153,9 @@ static int ____call_usermodehelper(void *data) goto fail; } - retval = kernel_execve(sub_info->path, sub_info->argv, sub_info->envp); + retval = kernel_execve(sub_info->path, + (const char *const *)sub_info->argv, + (const char *const *)sub_info->envp); /* Exec failed? */ fail: diff --git a/kernel/panic.c b/kernel/panic.c index 3b16cd93fa7d..4c13b1a88ebb 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -24,6 +24,9 @@ #include <linux/nmi.h> #include <linux/dmi.h> +#define PANIC_TIMER_STEP 100 +#define PANIC_BLINK_SPD 18 + int panic_on_oops; static unsigned long tainted_mask; static int pause_on_oops; @@ -36,36 +39,15 @@ ATOMIC_NOTIFIER_HEAD(panic_notifier_list); EXPORT_SYMBOL(panic_notifier_list); -/* Returns how long it waited in ms */ -long (*panic_blink)(long time); -EXPORT_SYMBOL(panic_blink); - -static void panic_blink_one_second(void) +static long no_blink(int state) { - static long i = 0, end; - - if (panic_blink) { - end = i + MSEC_PER_SEC; - - while (i < end) { - i += panic_blink(i); - mdelay(1); - i++; - } - } else { - /* - * When running under a hypervisor a small mdelay may get - * rounded up to the hypervisor timeslice. For example, with - * a 1ms in 10ms hypervisor timeslice we might inflate a - * mdelay(1) loop by 10x. - * - * If we have nothing to blink, spin on 1 second calls to - * mdelay to avoid this. - */ - mdelay(MSEC_PER_SEC); - } + return 0; } +/* Returns how long it waited in ms */ +long (*panic_blink)(int state); +EXPORT_SYMBOL(panic_blink); + /** * panic - halt the system * @fmt: The text string to print @@ -78,7 +60,8 @@ NORET_TYPE void panic(const char * fmt, ...) { static char buf[1024]; va_list args; - long i; + long i, i_next = 0; + int state = 0; /* * It's possible to come here directly from a panic-assertion and @@ -117,6 +100,9 @@ NORET_TYPE void panic(const char * fmt, ...) bust_spinlocks(0); + if (!panic_blink) + panic_blink = no_blink; + if (panic_timeout > 0) { /* * Delay timeout seconds before rebooting the machine. @@ -124,9 +110,13 @@ NORET_TYPE void panic(const char * fmt, ...) */ printk(KERN_EMERG "Rebooting in %d seconds..", panic_timeout); - for (i = 0; i < panic_timeout; i++) { + for (i = 0; i < panic_timeout * 1000; i += PANIC_TIMER_STEP) { touch_nmi_watchdog(); - panic_blink_one_second(); + if (i >= i_next) { + i += panic_blink(state ^= 1); + i_next = i + 3600 / PANIC_BLINK_SPD; + } + mdelay(PANIC_TIMER_STEP); } /* * This will not be a clean reboot, with everything @@ -152,9 +142,13 @@ NORET_TYPE void panic(const char * fmt, ...) } #endif local_irq_enable(); - while (1) { + for (i = 0; ; i += PANIC_TIMER_STEP) { touch_softlockup_watchdog(); - panic_blink_one_second(); + if (i >= i_next) { + i += panic_blink(state ^= 1); + i_next = i + 3600 / PANIC_BLINK_SPD; + } + mdelay(PANIC_TIMER_STEP); } } @@ -344,7 +338,7 @@ static int init_oops_id(void) } late_initcall(init_oops_id); -static void print_oops_end_marker(void) +void print_oops_end_marker(void) { init_oops_id(); printk(KERN_WARNING "---[ end trace %016llx ]---\n", diff --git a/kernel/params.c b/kernel/params.c index 0b30ecd53a52..08107d181758 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -31,6 +31,42 @@ #define DEBUGP(fmt, a...) #endif +/* Protects all parameters, and incidentally kmalloced_param list. */ +static DEFINE_MUTEX(param_lock); + +/* This just allows us to keep track of which parameters are kmalloced. */ +struct kmalloced_param { + struct list_head list; + char val[]; +}; +static LIST_HEAD(kmalloced_params); + +static void *kmalloc_parameter(unsigned int size) +{ + struct kmalloced_param *p; + + p = kmalloc(sizeof(*p) + size, GFP_KERNEL); + if (!p) + return NULL; + + list_add(&p->list, &kmalloced_params); + return p->val; +} + +/* Does nothing if parameter wasn't kmalloced above. */ +static void maybe_kfree_parameter(void *param) +{ + struct kmalloced_param *p; + + list_for_each_entry(p, &kmalloced_params, list) { + if (p->val == param) { + list_del(&p->list); + kfree(p); + break; + } + } +} + static inline char dash2underscore(char c) { if (c == '-') @@ -49,18 +85,25 @@ static inline int parameq(const char *input, const char *paramname) static int parse_one(char *param, char *val, - struct kernel_param *params, + const struct kernel_param *params, unsigned num_params, int (*handle_unknown)(char *param, char *val)) { unsigned int i; + int err; /* Find parameter */ for (i = 0; i < num_params; i++) { if (parameq(param, params[i].name)) { + /* Noone handled NULL, so do it here. */ + if (!val && params[i].ops->set != param_set_bool) + return -EINVAL; DEBUGP("They are equal! Calling %p\n", - params[i].set); - return params[i].set(val, ¶ms[i]); + params[i].ops->set); + mutex_lock(¶m_lock); + err = params[i].ops->set(val, ¶ms[i]); + mutex_unlock(¶m_lock); + return err; } } @@ -128,7 +171,7 @@ static char *next_arg(char *args, char **param, char **val) /* Args looks like "foo=bar,bar2 baz=fuz wiz". */ int parse_args(const char *name, char *args, - struct kernel_param *params, + const struct kernel_param *params, unsigned num, int (*unknown)(char *param, char *val)) { @@ -176,22 +219,29 @@ int parse_args(const char *name, /* Lazy bastard, eh? */ #define STANDARD_PARAM_DEF(name, type, format, tmptype, strtolfn) \ - int param_set_##name(const char *val, struct kernel_param *kp) \ + int param_set_##name(const char *val, const struct kernel_param *kp) \ { \ tmptype l; \ int ret; \ \ - if (!val) return -EINVAL; \ ret = strtolfn(val, 0, &l); \ if (ret == -EINVAL || ((type)l != l)) \ return -EINVAL; \ *((type *)kp->arg) = l; \ return 0; \ } \ - int param_get_##name(char *buffer, struct kernel_param *kp) \ + int param_get_##name(char *buffer, const struct kernel_param *kp) \ { \ return sprintf(buffer, format, *((type *)kp->arg)); \ - } + } \ + struct kernel_param_ops param_ops_##name = { \ + .set = param_set_##name, \ + .get = param_get_##name, \ + }; \ + EXPORT_SYMBOL(param_set_##name); \ + EXPORT_SYMBOL(param_get_##name); \ + EXPORT_SYMBOL(param_ops_##name) + STANDARD_PARAM_DEF(byte, unsigned char, "%c", unsigned long, strict_strtoul); STANDARD_PARAM_DEF(short, short, "%hi", long, strict_strtol); @@ -201,39 +251,50 @@ STANDARD_PARAM_DEF(uint, unsigned int, "%u", unsigned long, strict_strtoul); STANDARD_PARAM_DEF(long, long, "%li", long, strict_strtol); STANDARD_PARAM_DEF(ulong, unsigned long, "%lu", unsigned long, strict_strtoul); -int param_set_charp(const char *val, struct kernel_param *kp) +int param_set_charp(const char *val, const struct kernel_param *kp) { - if (!val) { - printk(KERN_ERR "%s: string parameter expected\n", - kp->name); - return -EINVAL; - } - if (strlen(val) > 1024) { printk(KERN_ERR "%s: string parameter too long\n", kp->name); return -ENOSPC; } - /* This is a hack. We can't need to strdup in early boot, and we + maybe_kfree_parameter(*(char **)kp->arg); + + /* This is a hack. We can't kmalloc in early boot, and we * don't need to; this mangled commandline is preserved. */ if (slab_is_available()) { - *(char **)kp->arg = kstrdup(val, GFP_KERNEL); + *(char **)kp->arg = kmalloc_parameter(strlen(val)+1); if (!*(char **)kp->arg) return -ENOMEM; + strcpy(*(char **)kp->arg, val); } else *(const char **)kp->arg = val; return 0; } +EXPORT_SYMBOL(param_set_charp); -int param_get_charp(char *buffer, struct kernel_param *kp) +int param_get_charp(char *buffer, const struct kernel_param *kp) { return sprintf(buffer, "%s", *((char **)kp->arg)); } +EXPORT_SYMBOL(param_get_charp); + +static void param_free_charp(void *arg) +{ + maybe_kfree_parameter(*((char **)arg)); +} + +struct kernel_param_ops param_ops_charp = { + .set = param_set_charp, + .get = param_get_charp, + .free = param_free_charp, +}; +EXPORT_SYMBOL(param_ops_charp); /* Actually could be a bool or an int, for historical reasons. */ -int param_set_bool(const char *val, struct kernel_param *kp) +int param_set_bool(const char *val, const struct kernel_param *kp) { bool v; @@ -258,8 +319,9 @@ int param_set_bool(const char *val, struct kernel_param *kp) *(int *)kp->arg = v; return 0; } +EXPORT_SYMBOL(param_set_bool); -int param_get_bool(char *buffer, struct kernel_param *kp) +int param_get_bool(char *buffer, const struct kernel_param *kp) { bool val; if (kp->flags & KPARAM_ISBOOL) @@ -270,9 +332,16 @@ int param_get_bool(char *buffer, struct kernel_param *kp) /* Y and N chosen as being relatively non-coder friendly */ return sprintf(buffer, "%c", val ? 'Y' : 'N'); } +EXPORT_SYMBOL(param_get_bool); + +struct kernel_param_ops param_ops_bool = { + .set = param_set_bool, + .get = param_get_bool, +}; +EXPORT_SYMBOL(param_ops_bool); /* This one must be bool. */ -int param_set_invbool(const char *val, struct kernel_param *kp) +int param_set_invbool(const char *val, const struct kernel_param *kp) { int ret; bool boolval; @@ -285,18 +354,26 @@ int param_set_invbool(const char *val, struct kernel_param *kp) *(bool *)kp->arg = !boolval; return ret; } +EXPORT_SYMBOL(param_set_invbool); -int param_get_invbool(char *buffer, struct kernel_param *kp) +int param_get_invbool(char *buffer, const struct kernel_param *kp) { return sprintf(buffer, "%c", (*(bool *)kp->arg) ? 'N' : 'Y'); } +EXPORT_SYMBOL(param_get_invbool); + +struct kernel_param_ops param_ops_invbool = { + .set = param_set_invbool, + .get = param_get_invbool, +}; +EXPORT_SYMBOL(param_ops_invbool); /* We break the rule and mangle the string. */ static int param_array(const char *name, const char *val, unsigned int min, unsigned int max, void *elem, int elemsize, - int (*set)(const char *, struct kernel_param *kp), + int (*set)(const char *, const struct kernel_param *kp), u16 flags, unsigned int *num) { @@ -309,12 +386,6 @@ static int param_array(const char *name, kp.arg = elem; kp.flags = flags; - /* No equals sign? */ - if (!val) { - printk(KERN_ERR "%s: expects arguments\n", name); - return -EINVAL; - } - *num = 0; /* We expect a comma-separated list of values. */ do { @@ -330,6 +401,7 @@ static int param_array(const char *name, /* nul-terminate and parse */ save = val[len]; ((char *)val)[len] = '\0'; + BUG_ON(!mutex_is_locked(¶m_lock)); ret = set(val, &kp); if (ret != 0) @@ -347,17 +419,17 @@ static int param_array(const char *name, return 0; } -int param_array_set(const char *val, struct kernel_param *kp) +static int param_array_set(const char *val, const struct kernel_param *kp) { const struct kparam_array *arr = kp->arr; unsigned int temp_num; return param_array(kp->name, val, 1, arr->max, arr->elem, - arr->elemsize, arr->set, kp->flags, + arr->elemsize, arr->ops->set, kp->flags, arr->num ?: &temp_num); } -int param_array_get(char *buffer, struct kernel_param *kp) +static int param_array_get(char *buffer, const struct kernel_param *kp) { int i, off, ret; const struct kparam_array *arr = kp->arr; @@ -368,7 +440,8 @@ int param_array_get(char *buffer, struct kernel_param *kp) if (i) buffer[off++] = ','; p.arg = arr->elem + arr->elemsize * i; - ret = arr->get(buffer + off, &p); + BUG_ON(!mutex_is_locked(¶m_lock)); + ret = arr->ops->get(buffer + off, &p); if (ret < 0) return ret; off += ret; @@ -377,14 +450,27 @@ int param_array_get(char *buffer, struct kernel_param *kp) return off; } -int param_set_copystring(const char *val, struct kernel_param *kp) +static void param_array_free(void *arg) +{ + unsigned int i; + const struct kparam_array *arr = arg; + + if (arr->ops->free) + for (i = 0; i < (arr->num ? *arr->num : arr->max); i++) + arr->ops->free(arr->elem + arr->elemsize * i); +} + +struct kernel_param_ops param_array_ops = { + .set = param_array_set, + .get = param_array_get, + .free = param_array_free, +}; +EXPORT_SYMBOL(param_array_ops); + +int param_set_copystring(const char *val, const struct kernel_param *kp) { const struct kparam_string *kps = kp->str; - if (!val) { - printk(KERN_ERR "%s: missing param set value\n", kp->name); - return -EINVAL; - } if (strlen(val)+1 > kps->maxlen) { printk(KERN_ERR "%s: string doesn't fit in %u chars.\n", kp->name, kps->maxlen-1); @@ -393,12 +479,20 @@ int param_set_copystring(const char *val, struct kernel_param *kp) strcpy(kps->string, val); return 0; } +EXPORT_SYMBOL(param_set_copystring); -int param_get_string(char *buffer, struct kernel_param *kp) +int param_get_string(char *buffer, const struct kernel_param *kp) { const struct kparam_string *kps = kp->str; return strlcpy(buffer, kps->string, kps->maxlen); } +EXPORT_SYMBOL(param_get_string); + +struct kernel_param_ops param_ops_string = { + .set = param_set_copystring, + .get = param_get_string, +}; +EXPORT_SYMBOL(param_ops_string); /* sysfs output in /sys/modules/XYZ/parameters/ */ #define to_module_attr(n) container_of(n, struct module_attribute, attr) @@ -409,7 +503,7 @@ extern struct kernel_param __start___param[], __stop___param[]; struct param_attribute { struct module_attribute mattr; - struct kernel_param *param; + const struct kernel_param *param; }; struct module_param_attrs @@ -428,10 +522,12 @@ static ssize_t param_attr_show(struct module_attribute *mattr, int count; struct param_attribute *attribute = to_param_attr(mattr); - if (!attribute->param->get) + if (!attribute->param->ops->get) return -EPERM; - count = attribute->param->get(buf, attribute->param); + mutex_lock(¶m_lock); + count = attribute->param->ops->get(buf, attribute->param); + mutex_unlock(¶m_lock); if (count > 0) { strcat(buf, "\n"); ++count; @@ -447,10 +543,12 @@ static ssize_t param_attr_store(struct module_attribute *mattr, int err; struct param_attribute *attribute = to_param_attr(mattr); - if (!attribute->param->set) + if (!attribute->param->ops->set) return -EPERM; - err = attribute->param->set(buf, attribute->param); + mutex_lock(¶m_lock); + err = attribute->param->ops->set(buf, attribute->param); + mutex_unlock(¶m_lock); if (!err) return len; return err; @@ -464,6 +562,18 @@ static ssize_t param_attr_store(struct module_attribute *mattr, #endif #ifdef CONFIG_SYSFS +void __kernel_param_lock(void) +{ + mutex_lock(¶m_lock); +} +EXPORT_SYMBOL(__kernel_param_lock); + +void __kernel_param_unlock(void) +{ + mutex_unlock(¶m_lock); +} +EXPORT_SYMBOL(__kernel_param_unlock); + /* * add_sysfs_param - add a parameter to sysfs * @mk: struct module_kobject @@ -475,7 +585,7 @@ static ssize_t param_attr_store(struct module_attribute *mattr, * if there's an error. */ static __modinit int add_sysfs_param(struct module_kobject *mk, - struct kernel_param *kp, + const struct kernel_param *kp, const char *name) { struct module_param_attrs *new; @@ -557,7 +667,7 @@ static void free_module_param_attrs(struct module_kobject *mk) * /sys/module/[mod->name]/parameters/ */ int module_param_sysfs_setup(struct module *mod, - struct kernel_param *kparam, + const struct kernel_param *kparam, unsigned int num_params) { int i, err; @@ -602,7 +712,11 @@ void module_param_sysfs_remove(struct module *mod) void destroy_params(const struct kernel_param *params, unsigned num) { - /* FIXME: This should free kmalloced charp parameters. It doesn't. */ + unsigned int i; + + for (i = 0; i < num; i++) + if (params[i].ops->free) + params[i].ops->free(params[i].arg); } static void __init kernel_add_sysfs_param(const char *name, @@ -768,28 +882,3 @@ static int __init param_sysfs_init(void) subsys_initcall(param_sysfs_init); #endif /* CONFIG_SYSFS */ - -EXPORT_SYMBOL(param_set_byte); -EXPORT_SYMBOL(param_get_byte); -EXPORT_SYMBOL(param_set_short); -EXPORT_SYMBOL(param_get_short); -EXPORT_SYMBOL(param_set_ushort); -EXPORT_SYMBOL(param_get_ushort); -EXPORT_SYMBOL(param_set_int); -EXPORT_SYMBOL(param_get_int); -EXPORT_SYMBOL(param_set_uint); -EXPORT_SYMBOL(param_get_uint); -EXPORT_SYMBOL(param_set_long); -EXPORT_SYMBOL(param_get_long); -EXPORT_SYMBOL(param_set_ulong); -EXPORT_SYMBOL(param_get_ulong); -EXPORT_SYMBOL(param_set_charp); -EXPORT_SYMBOL(param_get_charp); -EXPORT_SYMBOL(param_set_bool); -EXPORT_SYMBOL(param_get_bool); -EXPORT_SYMBOL(param_set_invbool); -EXPORT_SYMBOL(param_get_invbool); -EXPORT_SYMBOL(param_array_set); -EXPORT_SYMBOL(param_array_get); -EXPORT_SYMBOL(param_set_copystring); -EXPORT_SYMBOL(param_get_string); diff --git a/kernel/pid.c b/kernel/pid.c index e9fd8c132d26..d55c6fb8d087 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -122,6 +122,43 @@ static void free_pidmap(struct upid *upid) atomic_inc(&map->nr_free); } +/* + * If we started walking pids at 'base', is 'a' seen before 'b'? + */ +static int pid_before(int base, int a, int b) +{ + /* + * This is the same as saying + * + * (a - base + MAXUINT) % MAXUINT < (b - base + MAXUINT) % MAXUINT + * and that mapping orders 'a' and 'b' with respect to 'base'. + */ + return (unsigned)(a - base) < (unsigned)(b - base); +} + +/* + * We might be racing with someone else trying to set pid_ns->last_pid. + * We want the winner to have the "later" value, because if the + * "earlier" value prevails, then a pid may get reused immediately. + * + * Since pids rollover, it is not sufficient to just pick the bigger + * value. We have to consider where we started counting from. + * + * 'base' is the value of pid_ns->last_pid that we observed when + * we started looking for a pid. + * + * 'pid' is the pid that we eventually found. + */ +static void set_last_pid(struct pid_namespace *pid_ns, int base, int pid) +{ + int prev; + int last_write = base; + do { + prev = last_write; + last_write = cmpxchg(&pid_ns->last_pid, prev, pid); + } while ((prev != last_write) && (pid_before(base, last_write, pid))); +} + static int alloc_pidmap(struct pid_namespace *pid_ns) { int i, offset, max_scan, pid, last = pid_ns->last_pid; @@ -132,7 +169,12 @@ static int alloc_pidmap(struct pid_namespace *pid_ns) pid = RESERVED_PIDS; offset = pid & BITS_PER_PAGE_MASK; map = &pid_ns->pidmap[pid/BITS_PER_PAGE]; - max_scan = (pid_max + BITS_PER_PAGE - 1)/BITS_PER_PAGE - !offset; + /* + * If last_pid points into the middle of the map->page we + * want to scan this bitmap block twice, the second time + * we start with offset == 0 (or RESERVED_PIDS). + */ + max_scan = DIV_ROUND_UP(pid_max, BITS_PER_PAGE) - !offset; for (i = 0; i <= max_scan; ++i) { if (unlikely(!map->page)) { void *page = kzalloc(PAGE_SIZE, GFP_KERNEL); @@ -154,20 +196,12 @@ static int alloc_pidmap(struct pid_namespace *pid_ns) do { if (!test_and_set_bit(offset, map->page)) { atomic_dec(&map->nr_free); - pid_ns->last_pid = pid; + set_last_pid(pid_ns, last, pid); return pid; } offset = find_next_offset(map, offset); pid = mk_pid(pid_ns, map, offset); - /* - * find_next_offset() found a bit, the pid from it - * is in-bounds, and if we fell back to the last - * bitmap block and the final block was the same - * as the starting point, pid is before last_pid. - */ - } while (offset < BITS_PER_PAGE && pid < pid_max && - (i != max_scan || pid < last || - !((last+1) & BITS_PER_PAGE_MASK))); + } while (offset < BITS_PER_PAGE && pid < pid_max); } if (map < &pid_ns->pidmap[(pid_max-1)/BITS_PER_PAGE]) { ++map; diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c index 996a4dec5f96..b7e4c362361b 100644 --- a/kernel/pm_qos_params.c +++ b/kernel/pm_qos_params.c @@ -212,15 +212,17 @@ EXPORT_SYMBOL_GPL(pm_qos_request_active); /** * pm_qos_add_request - inserts new qos request into the list - * @pm_qos_class: identifies which list of qos request to us + * @dep: pointer to a preallocated handle + * @pm_qos_class: identifies which list of qos request to use * @value: defines the qos request * * This function inserts a new entry in the pm_qos_class list of requested qos * performance characteristics. It recomputes the aggregate QoS expectations - * for the pm_qos_class of parameters, and returns the pm_qos_request list - * element as a handle for use in updating and removal. Call needs to save - * this handle for later use. + * for the pm_qos_class of parameters and initializes the pm_qos_request_list + * handle. Caller needs to save this handle for later use in updates and + * removal. */ + void pm_qos_add_request(struct pm_qos_request_list *dep, int pm_qos_class, s32 value) { @@ -348,7 +350,7 @@ static int pm_qos_power_open(struct inode *inode, struct file *filp) pm_qos_class = find_pm_qos_object_by_minor(iminor(inode)); if (pm_qos_class >= 0) { - struct pm_qos_request_list *req = kzalloc(GFP_KERNEL, sizeof(*req)); + struct pm_qos_request_list *req = kzalloc(sizeof(*req), GFP_KERNEL); if (!req) return -ENOMEM; diff --git a/kernel/power/poweroff.c b/kernel/power/poweroff.c index e8b337006276..d52359374e85 100644 --- a/kernel/power/poweroff.c +++ b/kernel/power/poweroff.c @@ -24,7 +24,7 @@ static void do_poweroff(struct work_struct *dummy) static DECLARE_WORK(poweroff_work, do_poweroff); -static void handle_poweroff(int key, struct tty_struct *tty) +static void handle_poweroff(int key) { /* run sysrq poweroff on boot cpu */ schedule_work_on(cpumask_first(cpu_online_mask), &poweroff_work); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 74a3d693c196..f34d798ef4a2 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -324,26 +324,32 @@ int ptrace_detach(struct task_struct *child, unsigned int data) } /* - * Detach all tasks we were using ptrace on. + * Detach all tasks we were using ptrace on. Called with tasklist held + * for writing, and returns with it held too. But note it can release + * and reacquire the lock. */ void exit_ptrace(struct task_struct *tracer) { struct task_struct *p, *n; LIST_HEAD(ptrace_dead); - write_lock_irq(&tasklist_lock); + if (likely(list_empty(&tracer->ptraced))) + return; + list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) { if (__ptrace_detach(tracer, p)) list_add(&p->ptrace_entry, &ptrace_dead); } - write_unlock_irq(&tasklist_lock); + write_unlock_irq(&tasklist_lock); BUG_ON(!list_empty(&tracer->ptraced)); list_for_each_entry_safe(p, n, &ptrace_dead, ptrace_entry) { list_del_init(&p->ptrace_entry); release_task(p); } + + write_lock_irq(&tasklist_lock); } int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len) diff --git a/kernel/sched.c b/kernel/sched.c index 41541d79e3c8..09b574e7f4df 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3865,8 +3865,16 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) /* * Owner changed, break to re-assess state. */ - if (lock->owner != owner) + if (lock->owner != owner) { + /* + * If the lock has switched to a different owner, + * we likely have heavy contention. Return 0 to quit + * optimistic spinning and not contend further: + */ + if (lock->owner) + return 0; break; + } /* * Is that owner really running on that cpu? diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 806d1b227a21..ab661ebc4895 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -3752,6 +3752,8 @@ static void task_fork_fair(struct task_struct *p) raw_spin_lock_irqsave(&rq->lock, flags); + update_rq_clock(rq); + if (unlikely(task_cpu(p) != this_cpu)) __set_task_cpu(p, this_cpu); diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index e14c839e9faa..77e930d08e09 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -284,6 +284,33 @@ void ktime_get_ts(struct timespec *ts) } EXPORT_SYMBOL_GPL(ktime_get_ts); + +/** + * getnsboottime - get the bootbased clock in nsec format + * + * The function calculates the bootbased clock from the realtime + * clock and the wall_to_monotonic offset and stores the result + * in normalized timespec format in the variable pointed to by @ts. + */ +s64 getnsboottime(void) +{ + unsigned int seq; + s64 secs, nsecs; + + WARN_ON(timekeeping_suspended); + + do { + seq = read_seqbegin(&xtime_lock); + secs = xtime.tv_sec + wall_to_monotonic.tv_sec; + secs += total_sleep_time.tv_sec; + nsecs = xtime.tv_nsec + wall_to_monotonic.tv_nsec; + nsecs += total_sleep_time.tv_nsec + timekeeping_get_ns(); + + } while (read_seqretry(&xtime_lock, seq)); + return nsecs + (secs * NSEC_PER_SEC); +} +EXPORT_SYMBOL_GPL(getnsboottime); + /** * do_gettimeofday - Returns the time of day in a timeval * @tv: pointer to the timeval to be set @@ -690,6 +717,7 @@ static void timekeeping_adjust(s64 offset) static cycle_t logarithmic_accumulation(cycle_t offset, int shift) { u64 nsecps = (u64)NSEC_PER_SEC << timekeeper.shift; + u64 raw_nsecs; /* If the offset is smaller then a shifted interval, do nothing */ if (offset < timekeeper.cycle_interval<<shift) @@ -706,12 +734,15 @@ static cycle_t logarithmic_accumulation(cycle_t offset, int shift) second_overflow(); } - /* Accumulate into raw time */ - raw_time.tv_nsec += timekeeper.raw_interval << shift;; - while (raw_time.tv_nsec >= NSEC_PER_SEC) { - raw_time.tv_nsec -= NSEC_PER_SEC; - raw_time.tv_sec++; + /* Accumulate raw time */ + raw_nsecs = timekeeper.raw_interval << shift; + raw_nsecs += raw_time.tv_nsec; + if (raw_nsecs >= NSEC_PER_SEC) { + u64 raw_secs = raw_nsecs; + raw_nsecs = do_div(raw_secs, NSEC_PER_SEC); + raw_time.tv_sec += raw_secs; } + raw_time.tv_nsec = raw_nsecs; /* Accumulate error between NTP and clock interval */ timekeeper.ntp_error += tick_length << shift; diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 82499a5bdcb7..959f8d6c8cc1 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -710,6 +710,9 @@ static void blk_add_trace_rq(struct request_queue *q, struct request *rq, if (rq->cmd_flags & REQ_DISCARD) rw |= REQ_DISCARD; + if (rq->cmd_flags & REQ_SECURE) + rw |= REQ_SECURE; + if (rq->cmd_type == REQ_TYPE_BLOCK_PC) { what |= BLK_TC_ACT(BLK_TC_PC); __blk_add_trace(bt, 0, blk_rq_bytes(rq), rw, @@ -1816,6 +1819,8 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes) rwbs[i++] = 'S'; if (rw & REQ_META) rwbs[i++] = 'M'; + if (rw & REQ_SECURE) + rwbs[i++] = 'E'; rwbs[i] = '\0'; } @@ -1828,6 +1833,9 @@ void blk_fill_rwbs_rq(char *rwbs, struct request *rq) if (rq->cmd_flags & REQ_DISCARD) rw |= REQ_DISCARD; + if (rq->cmd_flags & REQ_SECURE) + rw |= REQ_SECURE; + bytes = blk_rq_bytes(rq); blk_fill_rwbs(rwbs, rw, bytes); diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index 3632ce87674f..19cccc3c3028 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -3846,6 +3846,9 @@ int ring_buffer_read_page(struct ring_buffer *buffer, rpos = reader->read; pos += size; + if (rpos >= commit) + break; + event = rb_reader_event(cpu_buffer); size = rb_event_length(event); } while (len > size); diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ba14a22be4cc..9ec59f541156 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3463,6 +3463,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *fpos) { char *buf; + size_t written; if (tracing_disabled) return -EINVAL; @@ -3484,11 +3485,15 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, } else buf[cnt] = '\0'; - cnt = mark_printk("%s", buf); + written = mark_printk("%s", buf); kfree(buf); - *fpos += cnt; + *fpos += written; - return cnt; + /* don't tell userspace we wrote more - it might confuse them */ + if (written > cnt) + written = cnt; + + return written; } static int tracing_clock_show(struct seq_file *m, void *v) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 09b4fa6e4d3b..4c758f146328 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -598,88 +598,165 @@ out: return ret; } -static void print_event_fields(struct trace_seq *s, struct list_head *head) +enum { + FORMAT_HEADER = 1, + FORMAT_PRINTFMT = 2, +}; + +static void *f_next(struct seq_file *m, void *v, loff_t *pos) { + struct ftrace_event_call *call = m->private; struct ftrace_event_field *field; + struct list_head *head; - list_for_each_entry_reverse(field, head, link) { - /* - * Smartly shows the array type(except dynamic array). - * Normal: - * field:TYPE VAR - * If TYPE := TYPE[LEN], it is shown: - * field:TYPE VAR[LEN] - */ - const char *array_descriptor = strchr(field->type, '['); + (*pos)++; - if (!strncmp(field->type, "__data_loc", 10)) - array_descriptor = NULL; + switch ((unsigned long)v) { + case FORMAT_HEADER: + head = &ftrace_common_fields; - if (!array_descriptor) { - trace_seq_printf(s, "\tfield:%s %s;\toffset:%u;" - "\tsize:%u;\tsigned:%d;\n", - field->type, field->name, field->offset, - field->size, !!field->is_signed); - } else { - trace_seq_printf(s, "\tfield:%.*s %s%s;\toffset:%u;" - "\tsize:%u;\tsigned:%d;\n", - (int)(array_descriptor - field->type), - field->type, field->name, - array_descriptor, field->offset, - field->size, !!field->is_signed); - } + if (unlikely(list_empty(head))) + return NULL; + + field = list_entry(head->prev, struct ftrace_event_field, link); + return field; + + case FORMAT_PRINTFMT: + /* all done */ + return NULL; + } + + head = trace_get_fields(call); + + /* + * To separate common fields from event fields, the + * LSB is set on the first event field. Clear it in case. + */ + v = (void *)((unsigned long)v & ~1L); + + field = v; + /* + * If this is a common field, and at the end of the list, then + * continue with main list. + */ + if (field->link.prev == &ftrace_common_fields) { + if (unlikely(list_empty(head))) + return NULL; + field = list_entry(head->prev, struct ftrace_event_field, link); + /* Set the LSB to notify f_show to print an extra newline */ + field = (struct ftrace_event_field *) + ((unsigned long)field | 1); + return field; } + + /* If we are done tell f_show to print the format */ + if (field->link.prev == head) + return (void *)FORMAT_PRINTFMT; + + field = list_entry(field->link.prev, struct ftrace_event_field, link); + + return field; } -static ssize_t -event_format_read(struct file *filp, char __user *ubuf, size_t cnt, - loff_t *ppos) +static void *f_start(struct seq_file *m, loff_t *pos) { - struct ftrace_event_call *call = filp->private_data; - struct list_head *head; - struct trace_seq *s; - char *buf; - int r; + loff_t l = 0; + void *p; - if (*ppos) + /* Start by showing the header */ + if (!*pos) + return (void *)FORMAT_HEADER; + + p = (void *)FORMAT_HEADER; + do { + p = f_next(m, p, &l); + } while (p && l < *pos); + + return p; +} + +static int f_show(struct seq_file *m, void *v) +{ + struct ftrace_event_call *call = m->private; + struct ftrace_event_field *field; + const char *array_descriptor; + + switch ((unsigned long)v) { + case FORMAT_HEADER: + seq_printf(m, "name: %s\n", call->name); + seq_printf(m, "ID: %d\n", call->event.type); + seq_printf(m, "format:\n"); return 0; - s = kmalloc(sizeof(*s), GFP_KERNEL); - if (!s) - return -ENOMEM; + case FORMAT_PRINTFMT: + seq_printf(m, "\nprint fmt: %s\n", + call->print_fmt); + return 0; + } - trace_seq_init(s); + /* + * To separate common fields from event fields, the + * LSB is set on the first event field. Clear it and + * print a newline if it is set. + */ + if ((unsigned long)v & 1) { + seq_putc(m, '\n'); + v = (void *)((unsigned long)v & ~1L); + } - trace_seq_printf(s, "name: %s\n", call->name); - trace_seq_printf(s, "ID: %d\n", call->event.type); - trace_seq_printf(s, "format:\n"); + field = v; - /* print common fields */ - print_event_fields(s, &ftrace_common_fields); + /* + * Smartly shows the array type(except dynamic array). + * Normal: + * field:TYPE VAR + * If TYPE := TYPE[LEN], it is shown: + * field:TYPE VAR[LEN] + */ + array_descriptor = strchr(field->type, '['); - trace_seq_putc(s, '\n'); + if (!strncmp(field->type, "__data_loc", 10)) + array_descriptor = NULL; - /* print event specific fields */ - head = trace_get_fields(call); - print_event_fields(s, head); + if (!array_descriptor) + seq_printf(m, "\tfield:%s %s;\toffset:%u;\tsize:%u;\tsigned:%d;\n", + field->type, field->name, field->offset, + field->size, !!field->is_signed); + else + seq_printf(m, "\tfield:%.*s %s%s;\toffset:%u;\tsize:%u;\tsigned:%d;\n", + (int)(array_descriptor - field->type), + field->type, field->name, + array_descriptor, field->offset, + field->size, !!field->is_signed); - r = trace_seq_printf(s, "\nprint fmt: %s\n", call->print_fmt); + return 0; +} - if (!r) { - /* - * ug! The format output is bigger than a PAGE!! - */ - buf = "FORMAT TOO BIG\n"; - r = simple_read_from_buffer(ubuf, cnt, ppos, - buf, strlen(buf)); - goto out; - } +static void f_stop(struct seq_file *m, void *p) +{ +} - r = simple_read_from_buffer(ubuf, cnt, ppos, - s->buffer, s->len); - out: - kfree(s); - return r; +static const struct seq_operations trace_format_seq_ops = { + .start = f_start, + .next = f_next, + .stop = f_stop, + .show = f_show, +}; + +static int trace_format_open(struct inode *inode, struct file *file) +{ + struct ftrace_event_call *call = inode->i_private; + struct seq_file *m; + int ret; + + ret = seq_open(file, &trace_format_seq_ops); + if (ret < 0) + return ret; + + m = file->private_data; + m->private = call; + + return 0; } static ssize_t @@ -877,8 +954,10 @@ static const struct file_operations ftrace_enable_fops = { }; static const struct file_operations ftrace_event_format_fops = { - .open = tracing_open_generic, - .read = event_format_read, + .open = trace_format_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release, }; static const struct file_operations ftrace_event_id_fops = { diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c index 6bff23625781..6f233698518e 100644 --- a/kernel/trace/trace_functions_graph.c +++ b/kernel/trace/trace_functions_graph.c @@ -507,7 +507,15 @@ get_return_for_leaf(struct trace_iterator *iter, * if the output fails. */ data->ent = *curr; - data->ret = *next; + /* + * If the next event is not a return type, then + * we only care about what type it is. Otherwise we can + * safely copy the entire event. + */ + if (next->ent.type == TRACE_GRAPH_RET) + data->ret = *next; + else + data->ret.ent.type = next->ent.type; } } diff --git a/kernel/trace/trace_stack.c b/kernel/trace/trace_stack.c index 056468eae7cf..a6b7e0e0f3eb 100644 --- a/kernel/trace/trace_stack.c +++ b/kernel/trace/trace_stack.c @@ -249,7 +249,7 @@ static int trace_lookup_stack(struct seq_file *m, long i) { unsigned long addr = stack_dump_trace[i]; - return seq_printf(m, "%pF\n", (void *)addr); + return seq_printf(m, "%pS\n", (void *)addr); } static void print_disabled(struct seq_file *m) diff --git a/kernel/watchdog.c b/kernel/watchdog.c index 613bc1f04610..0d53c8e853b1 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -206,6 +206,9 @@ void watchdog_overflow_callback(struct perf_event *event, int nmi, struct perf_sample_data *data, struct pt_regs *regs) { + /* Ensure the watchdog never gets throttled */ + event->hw.interrupts = 0; + if (__get_cpu_var(watchdog_nmi_touch) == true) { __get_cpu_var(watchdog_nmi_touch) = false; return; diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 2994a0e3a61c..8bd600c020e5 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -35,6 +35,9 @@ #include <linux/lockdep.h> #include <linux/idr.h> +#define CREATE_TRACE_POINTS +#include <trace/events/workqueue.h> + #include "workqueue_sched.h" enum { @@ -1790,7 +1793,13 @@ static void process_one_work(struct worker *worker, struct work_struct *work) work_clear_pending(work); lock_map_acquire(&cwq->wq->lockdep_map); lock_map_acquire(&lockdep_map); + trace_workqueue_execute_start(work); f(work); + /* + * While we must be careful to not use "work" after this, the trace + * point will only record its address. + */ + trace_workqueue_execute_end(work); lock_map_release(&lockdep_map); lock_map_release(&cwq->wq->lockdep_map); |